© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6794
    Prev
    Next
    INDEX
    Explanations

    technical language involving chemical formulas, mathematical formulas, probabilities and units of measure

    oai_token-act-pair · gemini-2.0-flash

    mathematical notations and symbols

    np_token-act-pair-logits · gpt-4o-mini

    Scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.46
    endsection
    -0.44
    __);
    -0.43
    梨
    -0.41
     Tartar
    -0.41
    MFC
    -0.41
    يتم
    -0.40
    Sub
    -0.40
    ฤษ
    -0.40
     sub
    -0.40
    POSITIVE LOGITS
     صوتيه
    0.78
    (−
    0.77
    {(-
    0.73
     inverse
    0.72
     (−
    0.71
    +:+
    0.69
     negativos
    0.67
    ^{-
    0.66
    $^{-
    0.66
    enumi
    0.66
    Activations Density 3.341%

    No Known Activations